Condition-based Design of Variable Impedance Controllers from User Demonstrations

TL;DR

This paper introduces a method for designing variable impedance controllers using offline parameter tuning based on learning from demonstration, ensuring safety and performance through convex optimization and LMIs, validated on a robotic pulley task.

Contribution

It presents a novel convex optimization framework for condition-based tuning of variable impedance controllers derived from demonstrations, incorporating safety and performance constraints.

Findings

Successful application to a 7-DoF robot for pulley task

Reduced exerted force compared to standard controllers

Ability to adapt controllers for task modifications without new demonstrations

Abstract

This paper presents an approach to ensure conditions on Variable Impedance Controllers through the off-line tuning of the parameters involved in its description. In particular, we prove its application to term modulations defined by a Learning from Demonstration technique. This is performed through the assessment of conditions regarding safety and performance, which encompass heuristics and constraints in the form of Linear Matrix Inequalities. Latter ones allow to define a convex optimisation problem to analyse their fulfilment, and require a polytopic description of the VIC, in this case, obtained from its formulation as a discrete-time Linear Parameter Varying system. With respect to the current state-of-art, this approach only limits the term definition obtained by the Learning from Demonstration technique to be continuous and function of exogenous signals, i.e. external variables to the robot. Therefore, using a solution-search method, the most suitable set of parameters according to assessment criteria can be obtained. Using a 7-DoF Kinova Gen3 manipulator, validation and comparison against solutions with relaxed conditions are performed. The method is applied to generate Variable Impedance Controllers for a pulley belt looping task, inspired by the Assembly Challenge for Industrial Robotics in World Robot Summit 2018, to reduce the exerted force with respect to a standard (constant) Impedance Controller. Additionally, method agility is evaluated on the generation of controllers for one-off modifications of the nominal belt looping task setup without new demonstrations.